Anthropic model product
Claude Sonnet 3.7
The most intelligent Claude model and the first hybrid reasoning model on the market.
Updated Aug 12, 2026. Default version: Claude 3.7 Sonnet
LLMBoard score38.7Claude 3.7 Sonnet
Coverage100%11 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable
Claude Sonnet 3.7 Specifications
Technical details for the model's default version.
- Version
- Claude 3.7 Sonnet
- Released
- Feb 24, 2025
- Knowledge cutoff
- Oct 31, 2024
- Parameters
- N/A
- Context window
- 200K
- Max output
- 64K
- Inputs
- image, pdf, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Sonnet 3.7 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Sonnet 3.7 Benchmark Results
Benchmark scores for Claude 3.7 Sonnet.
| TAU-bench Retail | 81.2% | 04 | 25 | 87.5% | C | |
| IFEval | 93.2% | 07 | 65 | 90.6% | C | |
| TAU-bench Airline | 58.4% | 09 | 23 | 63.6% | C | |
| MATH-500 | 96.2% | 14 | 32 | 58.1% | C | |
| Terminal-Bench | 35.2% | 14 | 25 | 45.8% | C | |
| MMMU | 75.0% | 22 | 63 | 66.1% | C | |
| MMMLU | 86.1% | 25 | 49 | 50.0% | C | |
| AIME 2024 | 80.0% | 28 | 53 | 48.1% | C | |
| GPQA | 84.8% | 55 | 234 | 76.8% | C | |
| SWE-Bench Verified | 70.3% | 58 | 105 | 45.2% | C | |
| AIME 2025 | 54.8% | 99 | 114 | 13.3% | C |
Claude Sonnet 3.7 Arena Results
Preference and agent-evaluation results for the default version.
| vision style control | overall | 74 | 1195.7 | 1,451 | N/A | |
| vision style control | overall | 85 | 1175.7 | 4,539 | N/A | |
| vision | overall | 88 | 1171.2 | 1,451 | N/A | |
| vision | overall | 98 | 1151.0 | 4,539 | N/A | |
| text style control | overall | 154 | 1387.9 | 38,882 | N/A | |
| text style control | overall | 171 | 1371.6 | 43,246 | N/A | |
| text | overall | 211 | 1314.8 | 38,882 | N/A | |
| text | overall | 219 | 1299.3 | 43,246 | N/A |
Claude Sonnet 3.7 Runtime Performance
Provider-specific output speed and catalog latency for Claude 3.7 Sonnet. Runtime does not affect the capability score.
| Bedrock | 101 tok/s | 0.5 s | 200K | 128K | |
| Anthropic | 42 tok/s | 0.4 s | 200K | 128K | |
| 42 tok/s | 0.4 s | 200K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Sonnet 3.7 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $3 input, $15 output per 1M via ZenMux
- Tracked offerings
- 5
| ZenMux | anthropic/claude-3.7-sonnet | global | $3 | $15 | 200K | |
| Abacus | claude-3-7-sonnet-20250219 | global | $3 | $15 | 200K | |
| DigitalOcean | anthropic-claude-3.7-sonnet | global | $3 | $15 | 200K | |
| Merge Gateway | anthropic/claude-3-7-sonnet-20250219 | global | $3 | $15 | 200K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Claude Sonnet 3.7 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Claude 3.7 Sonnet | 38.7 | N/A | 200K | 64K | No | Proprietary |
What is Claude Sonnet 3.7?
Key information about Claude Sonnet 3.7 and its available data.
The most intelligent Claude model and the first hybrid reasoning model on the market. 7 Sonnet can produce near-instant responses or extended, step-by-step thinking that is made visible to the user. Shows particularly strong improvements in coding and front-end web development.
Data as of 2026-08-11.
Claude Sonnet 3.7 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Claude Sonnet 3.7
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 4
Anthropic
AN
Claude Sonnet 3.5
Anthropic
AN
Claude Haiku 4.5
Anthropic
AN
Claude Opus 4
Anthropic
AN
Claude Opus 4.1
Anthropic
AN
Claude Sonnet 4.5
Anthropic
FAQ
Common questions about Claude Sonnet 3.7.
When was Claude Sonnet 3.7 released?
Claude Sonnet 3.7's default version was released on Feb 24, 2025.
How much does Claude Sonnet 3.7 cost?
No official standard PAYG price is currently available for Claude Sonnet 3.7. The lowest tracked third-party offer starts at $3 input and $15 output via ZenMux.
Who created Claude Sonnet 3.7?
Claude Sonnet 3.7 was created by Anthropic.
What is the context window for Claude Sonnet 3.7?
The default version has a 200K token context window.
Is Claude Sonnet 3.7 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Claude Sonnet 3.7?
5 provider offerings are linked to the default version.
What models should I compare Claude Sonnet 3.7 with?
Nearby ranked alternatives include DeepSeek-V3.1, Claude Sonnet 4, Mercury 2.